Improved Hyperspectral Anomaly Detection via Unsupervised Subspace Modeling in the Signed Cumulative Distribution Transform Domain

2025-09-30

AI Summary

In hyperspectral anomaly detection (HAD), limited prior knowledge and subtle spectral discrepancies between anomalies and background hinder accurate detection. To address this, we propose a novel unsupervised method grounded in transport theory: each pixel is modeled as a deformed observation of an underlying template, and the Signed Cumulative Distribution Transform (SCDT) is introduced—first in HAD—to derive robust, deformation-invariant pixel representations. Subsequently, unsupervised subspace learning is applied in the SCDT domain to precisely characterize the background manifold, while anomaly scores are quantified via reconstruction residuals. The method requires no labeled data and makes no assumptions about anomaly type or distribution. Evaluated on five standard benchmarks, it consistently outperforms state-of-the-art approaches, achieving an average 12.6% improvement in detection accuracy. Moreover, it demonstrates superior robustness to noise, scale variations, and complex background clutter.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Hyperspectral anomaly detection (HAD), a crucial approach for many civilian and military applications, seeks to identify pixels with spectral signatures that are anomalous relative to a preponderance of background signatures. Significant effort has been made to improve HAD techniques, but challenges arise due to complex real-world environments and, by definition, limited prior knowledge of potential signatures of interest. This paper introduces a novel HAD method by proposing a transport-based mathematical model to describe the pixels comprising a given hyperspectral image. In this approach, hyperspectral pixels are viewed as observations of a template pattern undergoing unknown deformations that enables their representation in the signed cumulative distribution transform (SCDT) domain. An unsupervised subspace modeling technique is then used to construct a model of abundant background signals in this domain, whereupon anomalous signals are detected as deviations from the learned model. Comprehensive evaluations across five distinct datasets illustrate the superiority of our approach compared to state-of-the-art methods.

Problem

• Detecting anomalous pixels in hyperspectral images
• Modeling background signals via unsupervised subspace learning
• Addressing limited prior knowledge of target signatures

Innovation

• Uses transport-based model for hyperspectral pixel representation
• Applies signed cumulative distribution transform domain analysis
• Employs unsupervised subspace modeling for anomaly detection